Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/techtheist/engramWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/techtheist/engram/claude-plugin)<a href="https://agentmods.dev/plugins/techtheist/engram/claude-plugin"><img src="https://agentmods.dev/badge/plugins/techtheist/engram/claude-plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/techtheist/engram/claude-plugin"><img src="https://agentmods.dev/badge/plugins/techtheist/engram/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
engram scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "engram",
"displayName": "Engram Alpha",
"version": "0.10.1",
"description": "Durable, local-first graph memory for AI coding assistants: decisions with reasons, gotchas, conflicts \u2014 inspectable and editable in a graph pane.",
"author": {
"name": "techtheist",
"url": "https://github.com/techtheist"
},
"homepage": "https://github.com/techtheist/engram",
"repository": "https://github.com/techtheist/engram",
"license": "MIT",
"keywords": [
"memory",
"knowledge-graph",
"mcp",
"local-first",
"decisions"
]
}
What it installs
The manifest is a name and a version. 2 skills, 3 commands, 1 MCP server travel with it, and installing the plugin installs all of them — 246 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed 6ac73cc5ac5b
- yesterday Changed f8ff25c7cf5c
- 5d ago Changed 7d272701a763
- 13d ago Changed 6d7110ac5001
- 17d ago Changed 38a7b818b1ea
- 21d ago Changed efcb9fdf68fd
- 27d ago Changed 787794e7d3d4
- 28d ago Changed e246771a3c15
- 1mo ago Changed e08fd823e684
- 1mo ago First seen · 21 lines scan A 93b38692bb3f
engram is a plugin published in the GitHub repository techtheist/engram (32 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
codemem
Persistent memory for Claude Code. Capture work across sessions and recall relevant context.
total-agent-memory
Persistent local memory for Claude Code — temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. Installs the MCP server, the memory-protocol skill and the capture hooks in one step.
second-brain
Agentic workflow with memory and tribal knowledge. Transforms Claude from goldfish to elephant with persistent knowledge across sessions.
memex
Collaborative memory for human-AI work — persistent, searchable, interconnected.
studiomeyer-memory
Hosted AI memory with 56 tools, including an interactive 3D knowledge graph. Semantic search, contradiction detection, multi-agent namespaces, import from ChatGPT, Claude, Gemini, Copilot and Perplexity. Recall runs on every prompt and the session closes itself, both without any setup. Magic Link auth, Hetzner…
studiomeyer-memory-chat
Use all 56 StudioMeyer Memory tools through your own OAuth account, with guided skills for sessions, recall, decisions, knowledge graph, proactive suggestions, and careful maintenance.